Minimalist Neural Networks training for phase classification in diluted-Ising models

Abstract

In this article, we explore the potential of artificial neural networks, which are trained using an exceptionally simplified catalog of ideal configurations encompassing both order and disorder. We explore the generalisation power of these networks to classify phases in complex models that are far from the simplified training context. As a paradigmatic case, we analyse the order-disorder transition of the diluted Ising model on several two-dimensional crystalline lattices, which does not have an exact solution and presents challenges for most of the available analytical and numerical techniques. Quantitative agreement is obtained in the determination of transition temperatures and percolation densities, with comparatively much more expensive methods. These findings highlight the potential of minimalist training in neural networks to describe complex phenomena and have implications beyond condensed matter physics.

9 figures

References in corpus (9)

• Machine-Learning Studies on Spin Models
• Deep Learning on the 2-Dimensional Ising Model to Extract the Crossover Region with a Variational Autoencoder
• Supervised and unsupervised learning of directed percolation
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Transfer learning of phase transitions in percolation and directed percolation
• Machine learning for percolation utilizing auxiliary Ising variables
• The percolating cluster is invisible to image recognition with deep learning
• Accelerating equilibrium spin-glass simulations using quantum annealers via generative deep learning

Cited by in corpus (2)

• Machine learning of phases and structures for model systems in physics
• Phase determination with and without deep learning